All projects/ ModelForge
ModelForge logoML deployment infrastructure

ModelForge.

Version a model. Release progressively. Preserve the stable service.

A model registry and deployment control plane with immutable artifacts, weighted canaries, promotion, rollback, and runtime boundaries.

MODELFORGE / RELEASE CONTROL
ModelForge / SYSTEM MAPModelForge logo
ArtifactSHA-256StableCanaryHealth gate

Register · canary · promote or recover

164 tests passedRECORDED CHECKPOINT
THE IDEA

What ModelForge does.

ModelForge is a model registry, deployment control plane and inference platform. Browser, CLI and API clients use the same operations to register immutable model versions, select a runtime, send a weighted share of requests to a canary and promote, abort or roll back a release.

Immutable model versions

Registered artifacts have SHA-256 identities, verified before execution, with local or S3-compatible storage behind one contract.

Progressive release controls

Weighted canaries receive controlled traffic. Promotion, abort and rollback preserve validated lifecycle transitions and environment targets.

Framework-independent execution

Built-in, PyTorch, and ONNX runtimes share an interface. A standalone Go inference runtime uses the external HTTP execution contract.

Runtime failure containment

Health inspection, bounded retries, circuit breakers, metrics and stable fallback govern execution at the runtime boundary.

BUILT WITH

The technology.

FROM INPUT TO OUTCOME

How it works.

Shipping a model is a release-management problem as well as an inference problem. An artifact must retain a verifiable identity, a candidate needs bounded exposure, and a failed new version must preserve the stable target.

Register

Create a workspace-scoped model and immutable version, then upload and verify its artifact.

ModelForge / SYSTEM MAPModelForge logo
ArtifactSHA-256StableCanaryHealth gate

Register · canary · promote or recover

ENGINEERING DECISIONS

Why it’s built this way.

Control plane and execution are separate

The Python/FastAPI control plane owns identity, state, traffic and tenancy. Runtimes own framework-specific loading and prediction, so a new framework does not require serving-path branches.

Atomic release invariants

A canary does not become stable until promotion succeeds. Promotion and rollback update release state and environment targets transactionally.

Workspace boundaries throughout

Models, artifacts, deployments, canaries and keys are workspace-scoped. Browser sessions use OIDC/PKCE; automation uses hashed workspace API keys.

RECORDED CHECKPOINTS

What the evidence shows.

The recorded CI checkpoint passed 164 Python tests with 3 skips. A hosted CI smoke benchmark completed 200/200 requests at 133.5 requests/s. The deployment validation scenario serves a baseline, observes weighted canary traffic, promotes v2, restores v1, detects an intentionally regressed v3, and aborts it while v1 remains authoritative.

164Python tests passed
200 / 200Successful CI smoke requests
133.5 /sHosted CI smoke throughput
RECORDED VALIDATION SCENARIO
Serve v1Canary v2Promote v2Restore v1Abort regressed v3

v1 remains authoritative after the deliberately failed canary.

SCOPE & LIMITS

The hosted CI smoke benchmark measures a bounded validation workload, not production capacity. ModelForge is not publicly hosted. The console preview uses illustrative example data. AWS/Terraform configuration is a deployment reference, and model caches and runtime client state are currently process-local.

Read the engineering brief PDF
OPEN THE WORK

Code, documents & proof.

A concise engineering brief and direct links to the implementation and supporting evidence.

ENGINEERING BRIEFModelForgeMichael Baffour Awuah · 2026

Inside the engineering

A two-page project brief covering the purpose, workflow, design decisions, recorded checks, and limits.